Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.)
Abstract Anti-nutritional factors can impact soybean nutrient bioavailability when consumed by monogastric animals. However, conventional methods available for quantifying anti-nutritional factors such as phytate and trypsin inhibitors in feeds are laboratory-intensive, time-consuming, expensive, an...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-06-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-07235-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850221811371868160 |
|---|---|
| author | Norberto Jose Palange Tonny Obua Julius Pyton Sserumaga Enoch Wembabazi Mildred Ochwo-Ssemakula Ephraim Nuwamanya Isaac Onziga Dramadri Moses Matovu Richard Edema Phinehas Tukamuhabwa |
| author_facet | Norberto Jose Palange Tonny Obua Julius Pyton Sserumaga Enoch Wembabazi Mildred Ochwo-Ssemakula Ephraim Nuwamanya Isaac Onziga Dramadri Moses Matovu Richard Edema Phinehas Tukamuhabwa |
| author_sort | Norberto Jose Palange |
| collection | DOAJ |
| description | Abstract Anti-nutritional factors can impact soybean nutrient bioavailability when consumed by monogastric animals. However, conventional methods available for quantifying anti-nutritional factors such as phytate and trypsin inhibitors in feeds are laboratory-intensive, time-consuming, expensive, and error-prone. This study developed near-infrared spectrophotometry (NIRS)-based models to quantify phytate and trypsin inhibitors in soybean. Thus, a set of 190 soybean genotypes assayed through conventional wet chemistry was used as a reference for model development and cross-validation. Using a benchtop NIR instrument (DS2500), spectra readings between 400 and 2500 nm were taken from each soybean sample. Mean values for phytate and total trypsin inhibitors (TTI) were 1.77 mg g−1 (SD = 1.23) and 0.89 mg g−1 (SD = 0.24), respectively. Predictive models were developed through partial least squares (PLS) and random forest (RF) regressions. The random forest models outperformed partial least squares regression with the best predictive performance of R2 test = 0.97; RPD = 5.95 and R2 test = 0.96; RPD = 3.62 for phytate and TTI, respectively. The high R2 and RPD values demonstrate the model's strong predictive capability and accuracy, suggesting that the NIRS-based models can effectively quantify phytate and TTI in soybean. Thus, breeders can efficiently select for low-anti-nutritional genotypes and accelerate the development of nutritionally beneficial legumes while reducing soybean processing costs. NIRS offers a promising alternative to traditional phenotyping methods due to its speed, simplicity, environmental friendliness, and cost-effectiveness. Its integration into breeding programs can streamline the screening process, especially in early selection stages. |
| format | Article |
| id | doaj-art-bed734ec00884437a1d42ae9d09b4e9d |
| institution | OA Journals |
| issn | 3004-9261 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Applied Sciences |
| spelling | doaj-art-bed734ec00884437a1d42ae9d09b4e9d2025-08-20T02:06:35ZengSpringerDiscover Applied Sciences3004-92612025-06-017611310.1007/s42452-025-07235-3Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.)Norberto Jose Palange0Tonny Obua1Julius Pyton Sserumaga2Enoch Wembabazi3Mildred Ochwo-Ssemakula4Ephraim Nuwamanya5Isaac Onziga Dramadri6Moses Matovu7Richard Edema8Phinehas Tukamuhabwa9Department of Crop Science and Horticulture, College of Agriculture and Environmental Science, Makerere UniversityDepartment of Crop Science and Horticulture, College of Agriculture and Environmental Science, Makerere UniversityNational Agricultural Resources Research Organization, Livestock Resources Research Institute (NaLIRRI)National Agricultural Resources Research Organization, National Crops Resources Research Institute (NaCRRI)Department of Crop Science and Horticulture, College of Agriculture and Environmental Science, Makerere UniversityDepartment of Crop Science and Horticulture, College of Agriculture and Environmental Science, Makerere UniversityDepartment of Crop Science and Horticulture, College of Agriculture and Environmental Science, Makerere UniversityNational Agricultural Resources Research Organization, Livestock Resources Research Institute (NaLIRRI)Department of Crop Science and Horticulture, College of Agriculture and Environmental Science, Makerere UniversityDepartment of Crop Science and Horticulture, College of Agriculture and Environmental Science, Makerere UniversityAbstract Anti-nutritional factors can impact soybean nutrient bioavailability when consumed by monogastric animals. However, conventional methods available for quantifying anti-nutritional factors such as phytate and trypsin inhibitors in feeds are laboratory-intensive, time-consuming, expensive, and error-prone. This study developed near-infrared spectrophotometry (NIRS)-based models to quantify phytate and trypsin inhibitors in soybean. Thus, a set of 190 soybean genotypes assayed through conventional wet chemistry was used as a reference for model development and cross-validation. Using a benchtop NIR instrument (DS2500), spectra readings between 400 and 2500 nm were taken from each soybean sample. Mean values for phytate and total trypsin inhibitors (TTI) were 1.77 mg g−1 (SD = 1.23) and 0.89 mg g−1 (SD = 0.24), respectively. Predictive models were developed through partial least squares (PLS) and random forest (RF) regressions. The random forest models outperformed partial least squares regression with the best predictive performance of R2 test = 0.97; RPD = 5.95 and R2 test = 0.96; RPD = 3.62 for phytate and TTI, respectively. The high R2 and RPD values demonstrate the model's strong predictive capability and accuracy, suggesting that the NIRS-based models can effectively quantify phytate and TTI in soybean. Thus, breeders can efficiently select for low-anti-nutritional genotypes and accelerate the development of nutritionally beneficial legumes while reducing soybean processing costs. NIRS offers a promising alternative to traditional phenotyping methods due to its speed, simplicity, environmental friendliness, and cost-effectiveness. Its integration into breeding programs can streamline the screening process, especially in early selection stages.https://doi.org/10.1007/s42452-025-07235-3SoybeansPhytateTrypsin inhibitorsNear-infrared spectrophotometry (NIRS)Partial least squaresRandom forest |
| spellingShingle | Norberto Jose Palange Tonny Obua Julius Pyton Sserumaga Enoch Wembabazi Mildred Ochwo-Ssemakula Ephraim Nuwamanya Isaac Onziga Dramadri Moses Matovu Richard Edema Phinehas Tukamuhabwa Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.) Discover Applied Sciences Soybeans Phytate Trypsin inhibitors Near-infrared spectrophotometry (NIRS) Partial least squares Random forest |
| title | Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.) |
| title_full | Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.) |
| title_fullStr | Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.) |
| title_full_unstemmed | Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.) |
| title_short | Artificial intelligence-driven near-infrared spectrophotometry model for rapid quantification of anti-nutritional factors in soybean (Glycine max.) |
| title_sort | artificial intelligence driven near infrared spectrophotometry model for rapid quantification of anti nutritional factors in soybean glycine max |
| topic | Soybeans Phytate Trypsin inhibitors Near-infrared spectrophotometry (NIRS) Partial least squares Random forest |
| url | https://doi.org/10.1007/s42452-025-07235-3 |
| work_keys_str_mv | AT norbertojosepalange artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT tonnyobua artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT juliuspytonsserumaga artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT enochwembabazi artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT mildredochwossemakula artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT ephraimnuwamanya artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT isaaconzigadramadri artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT mosesmatovu artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT richardedema artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax AT phinehastukamuhabwa artificialintelligencedrivennearinfraredspectrophotometrymodelforrapidquantificationofantinutritionalfactorsinsoybeanglycinemax |